This package provides a library for learning linear classifiers for large scale applications. It supports Support Vector Machines (SVM) with L2 and L1 loss, logistic regression, multi class classification and also Linear Programming Machines (L1-regularized SVMs). Its computational complexity scales linearly with the number of training examples making it one of the fastest SVM solvers around.
This package is known to build and work properly using an LFS-7.9 platform.
After updating this package from liblinear-1.96 or earlier, you need to reinstall Nmap-7.01, in order to link to the new library.
Download (HTTP): https://github.com/cjlin1/liblinear/archive/v210.tar.gz
Download MD5 sum: b48c811243eae0e4d144f21424294fcc
Download size: 376 KB
Estimated disk space required: 1.2 MB
Estimated build time: less than 0.1 SBU
The liblinear source tarball shown above downloads with the correct name, liblinear-210.tar.gz, if using a browser such as Firefox. If you prefer to use a command line program such as wget, you normally would obtain v210.tar.gz. To obtain this package with the proper filename, run:
wget -c https://github.com/cjlin1/liblinear/archive/v210.tar.gz \ -O liblinear-210.tar.gz
.
User Notes: http://wiki.linuxfromscratch.org/blfs/wiki/liblinear
Install liblinear by running the following commands:
make lib
This package does not come with a test suite.
Now, as the root
user:
install -vm644 linear.h /usr/include && install -vm755 liblinear.so.3 /usr/lib && ln -sfv liblinear.so.3 /usr/lib/liblinear.so
Last updated on 2016-03-04 15:42:06 -0800